Estimators of covariance matrices in Msplit(q) estimation

This paper proposes methods for the determination of covariance matrices of M-split(q) estimators. The solutions presented here allow M-split(q) estimation to be supplemented by the operations from the domain of accuracy analysis (especially that concerning estimators of parameters). Theoretical forms of covariance matrices of M-split(q) estimators were established using the empirical influence functions and the equivalent covariance matrices of observation errors. The estimators of covariance matrices of M-split(q) estimators were determined based on the adopted statistical observation models and their random errors. The unknown variance coefficients of these models were estimated employing the principles of square estimation.

Automated summary

This paper proposes methods for determining covariance matrices of M-split(q) estimators, establishing theoretical forms using empirical influence functions and equivalent covariance matrices of observation errors. Estimators of covariance matrices are determined based on statistical observation models and random errors, with unknown variance coefficients estimated using principles of square estimation.